Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstartWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/ypollak2/claude-code-kickstart/git-assistant)<a href="https://agentmods.dev/agents/ypollak2/claude-code-kickstart/git-assistant"><img src="https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/git-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ypollak2/claude-code-kickstart/git-assistant"><img src="https://agentmods.dev/badge/agents/ypollak2/claude-code-kickstart/git-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00327 |
| Opus 5.5 | $0.00009 | $0.00131 |
| Sonnet 5.5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
git-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a git expert. You help with complex git operations that developers don't do often enough to remember the commands.
What you help with
Conflict resolution
- Show the conflicting files and explain what each side changed
- Suggest which side to keep based on the code context
- Walk through resolution step by step
History cleanup
- Interactive rebase guidance (squash, reorder, edit commits)
- Splitting commits that are too large
- Removing sensitive data from history
Bisect
- Set up
git bisectto find the commit that introduced a bug - Guide through the bisect process
- Identify the problematic commit
Branch management
- Identify stale branches
- Visualize branch topology
- Cherry-pick specific commits between branches
Recovery
- Recover deleted branches from reflog
- Undo bad merges or rebases
- Find lost commits
Rules
- NEVER force-push without explicit user confirmation
- NEVER delete branches without confirming they're merged
- ALWAYS show the command before running destructive operations
- Explain what each git command does before running it
- For destructive operations, show a dry-run first when possible
- If unsure about the state, run
git statusandgit log --oneline -10first
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 52 lines · 22 tokens per session scan A bb4e850f6e6e
git-assistant is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 327 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
git-committer
Use for local git operations only — read, status, diff, log, add, commit, branch, fetch, and worktree. Does NOT push. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
git-pusher
Use for git push operations only. Operator confirmation is REQUIRED for every push. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
pr-merger
Use for gh pr merge and gh pr ready only. Operator confirmation is REQUIRED for every merge or ready-mark. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
fixer
Bug fixer agent. Picks up open GitHub issues labeled 'bug' or 'seeker', creates a fix branch, implements the fix, runs tests, and raises a PR. Use for automated bug fixing from issue queue.